[LLVMGPU] Outer Reductions should use TileAndFuse Pipeline for better performance#23988
Open
YashDeshpande25 wants to merge 1 commit intoiree-org:mainfrom
Open
[LLVMGPU] Outer Reductions should use TileAndFuse Pipeline for better performance#23988YashDeshpande25 wants to merge 1 commit intoiree-org:mainfrom
YashDeshpande25 wants to merge 1 commit intoiree-org:mainfrom
Conversation
Contributor
|
I think we need to talk about this a bit more |
Contributor
Can you post specific inputs? |
c1e0653 to
9d4dc1b
Compare
Contributor
Author
Discussed in meeting. |
Signed-off-by: Yash Deshpande <ydeshpan@amd.com>
9d4dc1b to
91ef99c
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds a check to select LLVMGPUTileAndFuse Pipeline when dealing with an outer reduction. This change is based on observed performance improvement when using TileAndFuse against VectorDistribute for outer reductions.
Summary of Stats for Context
On MI300X
On MI355
All comparisons were made against the VectorDistribute timings on the respective machines.